© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1544
    Prev
    Next
    INDEX
    Explanations

    various elements of source code in multiple computer languages, including some Spanish and Portuguese words.

    oai_token-act-pair · gemini-2.0-flash

    Code and console output

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UVWXYZ
    -0.71
     تضيفلها
    -0.69
    mybatisplus
    -0.69
    liferay
    -0.63
     reflector
    -0.60
    OGND
    -0.59
    twimg
    -0.58
    NgModule
    -0.58
    getWriter
    -0.57
    GenerationType
    -0.57
    POSITIVE LOGITS
    cite
    0.50
    cière
    0.48
     pylint
    0.47
     références
    0.46
    displayquote
    0.46
     Unter
    0.45
     voir
    0.44
    isch
    0.44
    irk
    0.43
    Portale
    0.43
    Activations Density 1.504%

    No Known Activations